On May 8, 2006, at 4:07 PM, Chris Hostetter wrote:
: I'd like to integrate the Lucene highlighting classes into Solr. Can
: anybody offer suggestions on where to start? I saw this on the Solr
: task list, so there must be someone on this list who has at least
: thought about this problem.
I'd been discussed, and i think Erik had an initial implimentation he
wasn't particularly happy with (but sounded decent to me).
Right, I implemented this (patch pasted below) but with hardcoded
field name and by retrieving the document again. The highlighted
text appears in a separate section than the actual hits, but aligned
with them sequentially. A more standard and configurable solution,
and of course one that is more efficient in getting the field data
(from the field cache I presume) would be better, but so far its
working well enough for a client demo.
Erik
package org.apache.solr.request;
import org.apache.lucene.search.*;
+import org.apache.lucene.search.highlight.*;
import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.SimpleAnalyzer;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
import java.util.List;
import java.util.Set;
import java.util.HashSet;
+import java.util.ArrayList;
import java.util.logging.Level;
import java.util.regex.Pattern;
import java.io.IOException;
+import java.io.StringReader;
import java.net.URL;
import org.apache.solr.util.StrUtils;
@@ -101,7 +109,8 @@
}
}
- DocList results = req.getSearcher().getDocList(query, null,
sort, req.getStart(), req.getLimit(), flags);
+ SolrIndexSearcher searcher = req.getSearcher();
+ DocList results = searcher.getDocList(query, null, sort,
req.getStart(), req.getLimit(), flags);
rsp.add(null,results);
if (debug!=null) {
@@ -123,6 +132,20 @@
rsp.add("debug",dbg);
}
+ boolean toHighlight = true;
+ if (toHighlight) {
+ DocIterator iterator = results.iterator();
+ ArrayList highlightedFields = new ArrayList();
+ while (iterator.hasNext()) {
+ int id = iterator.nextDoc();
+ Document doc = searcher.doc(id);
+ highlightedFields.add(highlight(doc.getField("body"),
query));
+ }
+
+ rsp.add("highlightedBody", highlightedFields);
+ }
+
+
} catch (SolrException e) {
rsp.setException(e);
numErrors++;
@@ -135,6 +158,22 @@
}
}
+ private Object highlight(Field field, Query query) throws
IOException {
+ QueryScorer scorer = new QueryScorer(query);
+ SimpleHTMLFormatter formatter =
+ new SimpleHTMLFormatter("<span class=\"highlight\">",
+ "</span>");
+ Highlighter highlighter = new Highlighter(formatter, scorer);
+ Fragmenter fragmenter = new SimpleFragmenter(50);
+ highlighter.setTextFragmenter(fragmenter);
+
+ String value = field.stringValue();
+ TokenStream tokenStream = new StandardAnalyzer()
+ .tokenStream(field.name(), new StringReader(value));
+
+ return highlighter.getBestFragments(tokenStream, value, 5, "...");
+ }
+
private NamedList getExplainList(Query query, DocList results,
SolrIndexSearcher searcher, IndexSchema schema) throws IOException {
NamedList explainList = new NamedList();
DocIterator iterator = results.iterator();
